Boosting the development of voice-enabled virtual assistants

Written by Livio Pugliese

September 22, 2022

PhoneMyBot by Interactive Media is a service that transforms chatbots, that work only on text conversations, into voice-enabled virtual assistants. To do this, PhoneMyBot terminates the voice channel – be it a telephone line, a recorded voice message, or other streaming voice channels, transforms the voice into text through a speech-to-text service, and sends the text over to the chatbot.

When PhoneMyBot receives the answer as a text message from the chatbot, it renders it into speech and pipes it back to the user. You can learn more about PhoneMyBot here.

There are many nuances and details that are missing from the description above (some of them are patent-pending), but a key to PhoneMyBot’s success is the ability to integrate with many chatbot platforms. PhoneMyBot offers a standard cloud API that chatbots can use, but it also includes adaptors that use the chatbot platforms’ native API, simulating a simple web client. This way, PhoneMyBot can communicate with existing chatbot deployments without the need for new developments in the chatbot code. At the moment, PhoneMyBot deploys adaptors for about 10 chatbot platforms, but new ones are coming out all the time, depending on our customers’ needs. If you don’t see an adaptor for your platform, let us know and we can add it.

Other Articles

This service was designed to make it cheap and immediate to add voice to an existing chatbot deployment – and it does that, but as an interesting side effect it also lowers the cost of new voicebot developments, while speeding up their deployment time.

Why is that? It all comes down to the dynamics of the conversational AI market for enterprise customers.

A successful conversational AI project entails more than just software and communications. It needs to be tailored to the company’s workflow, products and services, and lingo. Often, the type of language that needs to be used is not the same as in a general-purpose conversation, and this requires conversational applications to be trained to better support it. Of course, this is a common requirement in this type of project, and conversational AI platforms support language customization. But it still means that project development, testing, refining, and deployment take substantial time and effort.

Now, there are only so many conversational AI vendors offering voice integration, and system integrators who can use their platform to implement projects. In addition to the conversational AI part, a voice-enabled project includes integration with the telephone network or the corporate PBX, insertion into the IVR flow, and integration with the voice path in the contact center – both to forward calls if the virtual assistant cannot service them completely, and to provide call-associated data to human agents to make their work easier and provide better service.

All this requires specialized expertise, which few vendors have. These companies and people are in high demand, so delays can be long and costs high. 

But PhoneMyBot provides a ready alternative, with its pre-integrated voice channels. It includes telephone network and WhatsApp connectivity, and APIs to transfer calls to other voice endpoints (for instance, a contact center queue). Interactive Media has tons of experience integrating with the most common contact center suites both to insert the virtual assistant into the IVR flow and to send data attached to calls to the human agent who is servicing it.

This means that the pool of vendors that can bid on a voice-enabled conversational AI project is suddenly much bigger. Even companies with little or no voice expertise can now deliver a high-quality omnichannel virtual assistant: they only need to test their PhoneMyBot integration and iron out any small wrinkle that the additional channel may create in their conversational application strategy.

There are many more text-only conversational AI offers than voice-enabled ones. PhoneMyBot opens the omnichannel market to them, which benefits vendors, their customers, and ultimately the customer experience that you and I receive when we call a customer service line.

Other Articles

Making simple chatbots better

Making simple chatbots better

Many deployed chatbots are far from holding real conversations. But they too can be enabled for fluent dialog. This is how we do it.When you consider chatbots these days you think of ChatGPT, Google Bard, Bing Chat, etc. These are all based on Large Language Models...

read more
LLM-based chatbots and how to make them more reliable

LLM-based chatbots and how to make them more reliable

ChatGPT and its siblings are all the rage in customer service chatbots. This is fascinating and terrifying. How do we take the terror out of the equation?In the past year or so we witnessed an explosion of chatbots based on Large Language Models (LLM). The adoption of...

read more
Multimodal interactions: are they breaking through?

Multimodal interactions: are they breaking through?

Last week I watched a webinar and demo by a company providing tools and solutions for conversational customer service. Interactive Media, where I work, is in the same sector and I wanted to scoop out a competitor, see what they have and how they are presenting their...

read more

Interact with us

Subscription

Receive our exclusive content: